Segmental and transmural motion of the rat myocardium estimated using quantitative ultrasound with new strategies for infarct detection.

Introduction: The estimation of myocardial motion abnormalities has great potential for the early diagnosis of myocardial infarction (MI). This study aims to quantitatively analyze the segmental and transmural myocardial motion in MI rats by incorporating two novel strategies of algorithm parameter optimization and transmural motion index (TMI) calculation. Methods: Twenty-one rats were randomly divided into three groups (n = 7 per group): sham, MI, and ischemia-reperfusion (IR) groups. Ultrasound radio-frequency (RF) signals were acquired from each rat heart at 1 day and 28 days after animal model establishment; thus, a total of six datasets were represented as Sham1, Sham28, MI1, MI28, IR1, and IR28. The systolic cumulative displacement was calculated using our previously proposed vectorized normalized cross-correlation (VNCC) method. A semiautomatic regional and layer-specific myocardium segmentation framework was proposed for transmural and segmental myocardial motion estimation. Two novel strategies were proposed: the displacement-compensated cross-correlation coefficient (DCCCC) for algorithm parameter optimization and the transmural motion index (TMI) for quantitative estimation of the cross-wall transmural motion gradient. Results: The results showed that an overlap value of 80% used in VNCC guaranteed a more accurate displacement calculation. Compared to the Sham1 group, the systolic myocardial motion reductions were significantly detected (p < 0.05) in the middle anteroseptal (M-ANT-SEP), basal anteroseptal (B-ANT-SEP), apical lateral (A-LAT), middle inferolateral (M-INF-LAT), and basal inferolateral (B-INF-LAT) walls as well as a significant TMI drop (p < 0.05) in the M-ANT-SEP wall in the MI1 rats; significant motion reductions (p < 0.05) were also detected in the B-ANT-SEP and A-LAT walls in the IR1 group. The motion improvements (p < 0.05) were detected in the M-INF-LAT wall in the MI28 group and the apical septal (A-SEP) wall in the IR28 group compared to the MI1 and IR1 groups, respectively. Discussion: Our results show that the MI-induced reductions and reperfusion-induced recovery in systolic myocardial contractility could be successfully evaluated using our method, and most post-MI myocardial segments could recover systolic function to various extents in the remodeling phase. In conclusion, the ultrasound-based quantitative estimation framework for estimating segmental and transmural motion of the myocardium proposed in our study has great potential for non-invasive, novel, and early MI detection.

Preliminary study of generalized semiautomatic segmentation for 3D voxel labeling of lesions based on deep learning.

PURPOSE: The three-dimensional (3D) voxel labeling of lesions requires significant radiologists' effort in the development of computer-aided detection software. To reduce the time required for the 3D voxel labeling, we aimed to develop a generalized semiautomatic segmentation method based on deep learning via a data augmentation-based domain generalization framework. In this study, we investigated whether a generalized semiautomatic segmentation model trained using two types of lesion can segment previously unseen types of lesion. METHODS: We targeted lung nodules in chest CT images, liver lesions in hepatobiliary-phase images of Gd-EOB-DTPA-enhanced MR imaging, and brain metastases in contrast-enhanced MR images. For each lesion, the 32 × 32 × 32 isotropic volume of interest (VOI) around the center of gravity of the lesion was extracted. The VOI was input into a 3D U-Net model to define the label of the lesion. For each type of target lesion, we compared five types of data augmentation and two types of input data. RESULTS: For all considered target lesions, the highest dice coefficients among the training patterns were obtained when using a combination of the existing data augmentation-based domain generalization framework and random monochrome inversion and when using the resized VOI as the input image. The dice coefficients were 0.639 ± 0.124 for the lung nodules, 0.660 ± 0.137 for the liver lesions, and 0.727 ± 0.115 for the brain metastases. CONCLUSIONS: Our generalized semiautomatic segmentation model could label unseen three types of lesion with different contrasts from the surroundings. In addition, the resized VOI as the input image enables the adaptation to the various sizes of lesions even when the size distribution differed between the training set and the test set.

Manual and semiautomatic segmentation of bone sarcomas on MRI have high similarity

The aims of this study were to evaluate the intra- and interobserver reproducibility of manual segmentation of bone sarcomas in magnetic resonance imaging (MRI) studies and to compare manual and semiautomatic segmentation methods. This retrospective study included twelve osteosarcoma and eight Ewing sarcoma MRI studies performed prior to any therapeutic intervention. All cases were histopathologically confirmed. Three radiologists used 3D-Slicer software to perform manual segmentation of bone sarcomas in a blinded and independent manner. One radiologist segmented manually and also performed semiautomatic segmentation with the GrowCut tool. Segmentation exercises were timed for comparison. The dice similarity coefficient (DSC) and Hausdorff distance (HD) were used to evaluate similarity between the segmentation results and further statistical analyses were performed to compare DSC, HD, and volumetric results. Manual segmentation was reproducible with intraobserver DSC varying from 0.83 to 0.97 and HD from 3.37 to 28.73 mm. Interobserver DSC of manual segmentation showed variation from 0.73 to 0.97 and HD from 3.93 to 33.40 mm. Semiautomatic segmentation compared to manual segmentation resulted in DSCs of 0.71−0.96 and HDs of 5.38−31.54 mm. Semiautomatic segmentation required significantly less time compared to manual segmentation (P value ≤0.05). Among all situations compared, tumor volumetry did not show significant statistical differences (P value >0.05). We found excellent intra- and interobserver agreement for manual segmentation of osteosarcoma and Ewing sarcoma. There was high similarity between manual and semiautomatic segmentation, with a significant reduction of segmentation time using the semiautomatic method.

A robust segmentation method with triple-factor non-negative matrix factorization for myocardial blood flow quantification from dynamic 82 Rb positron emission tomography.

PURPOSE: In this work, we proposed a triple-factor non-negative matrix factorization (TNMF) method to semiautomatically segment the regions of interest (ROIs) of the left ventricular (LV) cavity and myocardium to improve the reproducibility of myocardial blood flow (MBF) quantification from dynamic 82 Rb positron emission tomography (PET). METHODS: The proposed TNMF method was evaluated using NCAT phantom simulation with three noise levels. The segmented ROIs, time-activity curves (TACs), and K1 derived from the TNMF method were compared with the ground truth simulated. The TNMF method was further evaluated in two patients each undergone both rest and stress 82 Rb PET studies. The TNMF and manual segmentations were implemented by two different observers, and the interoperator variations of MBF and myocardial flow reserve (MFR) were compared between the two methods. RESULTS: Our simulation results showed that the TNMF method for dynamic PET image segmentation was robust as evidenced by the high Dice similarity coefficient, regardless of high or low count level. The relative bias in K1 estimation was less than 1%. Our patient results also showed that reasonable ROIs for the LV cavity and myocardium could be obtained precisely for patients with and without myocardial perfusion defects. The TACs derived from the TNMF method were highly correlated with those obtained with the manual method (R2  ≥ 0.964). The interoperator variations of MBF and MFR were markedly reduced using the TNMF method. CONCLUSIONS: In conclusion, the TNMF method is highly feasible for semiautomatic segmentation of the LV cavity and myocardium, with the potential to improve the precision of MBF quantification by improving segmentation.

Reproducibility and non-redundancy of radiomic features extracted from arterial phase CT scans in hepatocellular carcinoma patients: impact of tumor segmentation variability.

BACKGROUND: The reproducibility and non-redundancy of radiomic features are challenges in accelerating the clinical translation of radiomics. In this study, we focused on the robustness and non-redundancy of radiomic features extracted from computed tomography (CT) scans in hepatocellular carcinoma (HCC) patients with respect to different tumor segmentation methods. METHODS: Arterial enhanced CT images were retrospectively randomly obtained from 106 patients. As a training data set, 26 HCC patients were used to calculate the features' reproducibility and redundancy. Another data set (55 HCC patients and 25 healthy volunteers) was used for classification. The GrowCut and GraphCut semiautomatic segmentation methods were implemented in 3D Slicer software by two independent observers, and manual delineation was performed by five abdominal radiation oncologists to acquire the gross tumor volume (GTV). Seventy-one radiomic features were extracted from GTVs using Imaging Biomarker Explorer (IBEX) software, including 17 tumor intensity statistical features, 16 shape features and 38 textural features. For each radiomic feature, intraclass correlation coefficient (ICC) and hierarchical clustering were used to quantify its reproducibility and redundancy. Features with ICC values greater than 0.75 were considered reproducible. To generate the number of non-redundancy feature subgroups, the R2 statistic method was used. Then, a classification model was built using a support vector machine (SVM) algorithm with 10-fold cross validation, and area under ROC curve (AUC) was used to evaluate the utility of non-redundant feature extraction by hierarchical clustering. RESULTS: The percentages of excellent reproducible features in the manual delineation group, GraphCut and GrowCut segmentation group were 69% [49], 73% [52] and 79% [56], respectively. Sixty-five percent [46] of the features showed strong robustness for all segmentation methods. The optimal number of cluster subgroup were 9, 13 and 11 for manual delineation, GraphCut and GrowCut segmentation, respectively. The optimal cluster subgroup number was 6 for all groups when the collectively high reproducibility features were selected for clustering. The receiver operating characteristic (ROC) analysis of radiomics classification model with and without feature reduction for healthy liver and HCC had an AUC value of 0.857 and 0.721 respectively. CONCLUSIONS: Our study demonstrates that variations exist in the reproducibility of quantitative imaging features extracted from tumor regions segmented using different methods. The reproducibility and non-redundancy of the radiomic features rely greatly on the tumor segmentation in HCC CT images. We recommend that the most reliable and uniform radiomic features should be selected in the clinical use of radiomics. Classification experiments with feature reduction showed that radiomic features were effective in identifying healthy liver and HCC.

Rapid and Accurate MRI Segmentation of Peritumoral Brain Edema in Meningiomas.

PURPOSE: The extent of peritumoral brain edema (PTBE) in meningiomas commonly affects the clinical outcome. Despite its importance, edema volume is usually highly inaccurately approximated to a spheroid shape. We tested the accuracy and the reproducibility of semiautomatic lesion management software for the analysis of PTBE in a homogeneous case series of surgically confirmed intracranial meningiomas. METHODS: PTBE volume was calculated on magnetic resonance images in 50 patients with intracranial meningiomas using commercial lesion management software (Vue PACS Livewire, Carestream, Rochester, NY, USA). Inter and intraobserver agreement evaluation and a comparison between manual volume calculation, the semiautomatic software and spheroid approximation were performed in 22 randomly selected patients. RESULTS: The calculation of edema volume was possible in all cases irrespective of the extent of the signal changes. The median time for each calculation was 3 min. Interobserver and intraobserver agreement confirmed the reproducibility of the method. Comparison with standard (fully manual) calculation confirmed the accuracy of this software. CONCLUSIONS: Our study showed a high level of reproducibility of this semiautomatic computational method for peritumoral brain edema. It is rapid and easy to use after relatively short training and is suitable for implementation in clinical practice.

Differentiation between Glioblastoma and Primary Central Nervous System Lymphoma Using Dynamic Susceptibility Contrast-Enhanced Perfusion MR Imaging: Comparison Study of the Manual versus Semiautomatic Segmentation Method

BACKGROUND: Normalized cerebral blood volume (nCBV) can be measured using manual or semiautomatic segmentation method. However, the difference in diagnostic performance on brain tumor differentiation between differently measured nCBV has not been evaluated. PURPOSE: To compare the diagnostic performance of manually obtained nCBV to that of semiautomatically obtained nCBV on glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL) differentiation. MATERIALS AND METHODS: Histopathologically confirmed forty GBM and eleven PCNSL patients underwent 3T MR imaging with dynamic susceptibility contrast-enhanced perfusion MR imaging before any treatment or biopsy. Based on the contrast-enhanced T1-weighted imaging, the mean nCBV (mCBV) was measured using the manual method (manual mCBV), random regions of interest (ROIs) placement by the observer, or the semiautomatic segmentation method (semiautomatic mCBV). The volume of enhancing portion of the tumor was also measured during semiautomatic segmentation process. T-test, ROC curve analysis, Fisher's exact test and multivariate regression analysis were performed to compare the value and evaluate the diagnostic performance of each parameter. RESULTS: GBM showed a higher enhancing volume (P = 0.0307), a higher manual mCBV (P = 0.018) and a higher semiautomatic mCBV (P = 0.0111) than that of the PCNSL. Semiautomatic mCBV had the highest value (0.815) for the area under the curve (AUC), however, the AUCs of the three parameters were not significantly different from each other. The semiautomatic mCBV was the best independent predictor for the GBM and PCNSL differential diagnosis according to the stepwise multiple regression analysis. CONCLUSION: We found that the semiautomatic mCBV could be a better predictor than the manual mCBV for the GBM and PCNSL differentiation. We believe that the semiautomatic segmentation method can contribute to the advancement of perfusion based brain tumor evaluation.

Semiautomatic tumor segmentation with multimodal images in a conditional random field framework.

Volumetric medical images of a single subject can be acquired using different imaging modalities, such as computed tomography, magnetic resonance imaging (MRI), and positron emission tomography. In this work, we present a semiautomatic segmentation algorithm that can leverage the synergies between different image modalities while integrating interactive human guidance. The algorithm provides a statistical segmentation framework partly automating the segmentation task while still maintaining critical human oversight. The statistical models presented are trained interactively using simple brush strokes to indicate tumor and nontumor tissues and using intermediate results within a patient's image study. To accomplish the segmentation, we construct the energy function in the conditional random field (CRF) framework. For each slice, the energy function is set using the estimated probabilities from both user brush stroke data and prior approved segmented slices within a patient study. The progressive segmentation is obtained using a graph-cut-based minimization. Although no similar semiautomated algorithm is currently available, we evaluated our method with an MRI data set from Medical Image Computing and Computer Assisted Intervention Society multimodal brain segmentation challenge (BRATS 2012 and 2013) against a similar fully automatic method based on CRF and a semiautomatic method based on grow-cut, and our method shows superior performance.

A technique for semiautomatic segmentation of echogenic structures in 3D ultrasound, applied to infant hip dysplasia.

PURPOSE: Automatic segmentation of anatomical structures and lesions from medical ultrasound images is a formidable challenge in medical imaging due to image noise, blur and artifacts. In this paper we present a segmentation technique with features highly suited to use in noisy 3D ultrasound volumes and demonstrate its use in modeling bone, specifically the acetabulum in infant hips. Quantification of the acetabular shape is crucial in diagnosing developmental dysplasia of the hip (DDH), a common condition associated with hip dislocation and premature osteoarthritis if not treated. The well-established Graf technique for DDH diagnosis has been criticized for high inter-observer and inter-scan variability. In our earlier work we have introduced a more reliable instability metric based on 3D ultrasound data. Visualizing and interpreting the acetabular shape from noisy 3D ultrasound volumes has been one of the major roadblocks in using 3D ultrasound as diagnostic tool for DDH. For this study we developed a semiautomated segmentation technique to rapidly generate 3D acetabular surface models and classified the acetabulum based on acetabular contact angle (ACA) derived from the models. We tested the feasibility and reliability of the technique compared with manual segmentation. METHODS: The proposed segmentation algorithm is based on graph search. We formulate segmentation of the acetabulum as an optimal path finding problem on an undirected weighted graph. Slice contours are defined as the optimal path passing through a set of user-defined seed points in the graph, and it can be found using dynamic programming techniques (in this case Dijkstra's algorithm). Slice contours are then interpolated over the 3D volume to generate the surface model. A three-dimensional ACA was calculated using normal vectors of the surface model. RESULTS: The algorithm was tested over an extensive dataset of 51 infant ultrasound hip volumes obtained from 42 subjects with normal to dysplastic hips. The contours generated by the segmentation algorithm closely matched with those obtained from manual segmentation. The average RMS errors between the semiautomated and manual segmentation for the 51 volumes were 0.28 mm/1.1 voxel (with 2 node points) and 0.24 mm/0.9 voxel (with 3 node points). The semiautomatic algorithm gave visually acceptable results on images with moderate levels of noise and was able to trace the boundary of the acetabulum even in the presence of significant shadowing. Semiautomatic contouring was also faster than manual segmentation at 37 versus 56 s per scan. It also improved the repeatability of the ACA calculation with inter-observer and intra-observer variability of 1.4 ± 0.9 degree and 1.4 ± 1.0 degree. CONCLUSION: The semiautomatic segmentation technique proposed in this work offers a fast and reliable method to delineate the contours of the acetabulum from 3D ultrasound volumes of the hip. Since the technique does not rely upon contour evolution, it is less susceptible than other methods to the frequent missing or incomplete boundaries and noise artifacts common in ultrasound images. ACA derived from the segmented 3D surface was able to accurately classify the acetabulum under the categories normal, borderline and dysplastic. The semiautomatic technique makes it easier to segment the volume and reduces the inter-observer and intra-observer variation in ACA calculation compared with manual segmentation. The method can be applied to any structure with an echogenic boundary on ultrasound (such as a ventricle, blood vessel, organ or tumor), or even to structures with a bright border on computed tomography or magnetic resonance imaging.

Semiautomatic segmentation of longitudinal computed tomography images in a rat model of lung injury by surfactant depletion.

Quantitative analysis of computed tomography (CT) is essential to the study of acute lung injury. However, quantitative CT is made difficult by poor lung aeration, which complicates the critical step of image segmentation. To overcome this obstacle, this study sought to develop and validate a semiautomated, multilandmark, registration-based scheme for lung segmentation that is effective in conditions of poor aeration. Expiratory and inspiratory CT images were obtained in rats (n = 8) with surfactant depletion of incremental severity to mimic worsening aeration. Trained operators manually delineated the images to provide a comparative landmark. Semiautomatic segmentation originated from a single, previously segmented reference image obtained at healthy baseline. Deformable registration of the target images (after surfactant depletion) was performed using the symmetric diffeomorphic transformation model with B-spline regularization. Registration used multiple landmarks (i.e., rib cage, spine, and lung parenchyma) to minimize the effect of poor aeration. Then target images were automatically segmented by applying the calculated transformation function to the reference image contour. Semiautomatically and manually segmented contours proved to be highly similar in all aeration conditions, including those characterized by more severe surfactant depletion and expiration. The Dice similarity coefficient was over 0.9 in most conditions, confirming high agreement, irrespective of poor aeration. Furthermore, CT density-based measurements of gas volume, tissue mass, and lung aeration distribution were minimally affected by the method of segmentation. Moving forward, multilandmark registration has the potential to streamline quantitative CT analysis by enabling semiautomatic image segmentation of lungs with a broad range of injury severity.

Semiautomatic Segmentation of Lung Region from Three Dimensional Color Images of Visible Human / 대한의료정보학회지

OBJECTIVE: Watershed algorithm is image segmentation algorithm divides the image into numerous small regions. This paper proposes a new approach to extract the lung region from the three dimensional color image of Frozen Human Body (Visible Human Male) based on watershed algorithm. METHODS: After applying this algorithm to input image and getting the small regions, we merge these small regions into one region with three measures based on color, edge marker, and SURFACE respectively. RESULTS: We can say that the smaller number of FALSE-POSITIVE and TRUE NEGATIVE voxels and the larger number of FALSE POSITIVE voxels are better result. Graph shows change in the number of voxel in above groups of the left lung detection when tau color change with tau em is 0.7. We think that the result at the range of tau color from 110 to 180 are better than the other results in Graph. CONCLUSION: Comparing with our previous work, we newly use Canny edge filter for edge marker and define SURFACE-based dissimilarity to relax the problem of its step. The users must select a point within the lung region and some thresholds (taucolor, tauem, tauhigh, taulow, delta) to detect the target region.